Knowledge Commons of Institute of Automation,CAS
Region-adaptive Concept Aggregation for Few-shot Visual Recognition | |
Mengya Han1,2,4; Yibing Zhan4; Baosheng Yu3; Yong Luo1,2; Han Hu5; Bo Du1,2; Yonggang Wen6; Dacheng Tao4 | |
发表期刊 | Machine Intelligence Research |
ISSN | 2731-538X |
2023 | |
卷号 | 20期号:4页码:554-568 |
摘要 | Few-shot learning (FSL) aims to learn novel concepts from very limited examples. However, most FSL methods suffer from the issue of lacking robustness in concept learning. Specifically, existing FSL methods usually ignore the diversity of region contents that may contain concept-irrelevant information such as the background, which would introduce bias/noise and degrade the performance of conceptual representation learning. To address the above-mentioned issue, we propose a novel metric-based FSL method termed region adaptive concept aggregation network or RCA-Net. Specifically, we devise a region-adaptive concept aggregator (RCA) to model the relationships of different regions and capture the conceptual information in different regions, which are then integrated in a weighted average manner to obtain the conceptual representation. Consequently, robust concept learning can be achieved by focusing more on the concept-relevant information and less on the conceptual-irrelevant information. We perform extensive experiments on three popular visual recognition benchmarks to demonstrate the superiority of RCA-Net for robust few-shot learning. In particular, on the Caltech UCSD Birds-200-2011 (CUB200) dataset, the proposed RCA-Net significantly improves 1-shot accuracy from 74.76% to 78.03% and 5-shot accuracy from 86.84% to 89.83% compared with the most competitive counterpart. |
关键词 | Few-shot learning, metric-based meta learning, concept learning, region-adaptive, concept-aggregation |
DOI | 10.1007/s11633-022-1358-8 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/55994 |
专题 | 学术期刊_Machine Intelligence Research |
作者单位 | 1.School of Computer Science, National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan 430072, China 2.Hubei Luojia Laboratory, Wuhan 430072, China 3.School of Computer Science, The University of Sydney, Sydney 2006, Australia 4.JD Explore Academy, Beijing 101116, China 5.School of Information and Electronics, Beijing Institute of Technology, Beijing 100081, China 6.School of Computer Science and Engineering, Nanyang Technological University, Singapore 639798, Singapore |
推荐引用方式 GB/T 7714 | Mengya Han,Yibing Zhan,Baosheng Yu,et al. Region-adaptive Concept Aggregation for Few-shot Visual Recognition[J]. Machine Intelligence Research,2023,20(4):554-568. |
APA | Mengya Han.,Yibing Zhan.,Baosheng Yu.,Yong Luo.,Han Hu.,...&Dacheng Tao.(2023).Region-adaptive Concept Aggregation for Few-shot Visual Recognition.Machine Intelligence Research,20(4),554-568. |
MLA | Mengya Han,et al."Region-adaptive Concept Aggregation for Few-shot Visual Recognition".Machine Intelligence Research 20.4(2023):554-568. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
MIR-2022-03-075.pdf(4324KB) | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论